-
Notifications
You must be signed in to change notification settings - Fork 0
/
main.py
372 lines (322 loc) · 12.6 KB
/
main.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
__author__ = 'vle020518'
import pandas as pd
import numpy as np
import warnings
warnings.filterwarnings("ignore")
from sklearn.neural_network import MLPClassifier
from sklearn.model_selection import train_test_split
from sklearn.svm import SVC
from kmeans import KMeans
from kernel_kmeans import Kernel_KMeans
from sklearn.linear_model import LogisticRegression
from sklearn.linear_model import RidgeClassifier
from sklearn.linear_model import SGDClassifier
from sklearn.linear_model import Perceptron
from sklearn.naive_bayes import BernoulliNB, MultinomialNB, GaussianNB
from sklearn.neighbors import KNeighborsClassifier
from sklearn.neighbors import NearestCentroid
from sklearn.ensemble import RandomForestClassifier
from multinomial_NB import multinomial_NB as MyMultinomialNB
from logistic_regression import logistic_regression
import csv
import sys
def ger_raw_data(fileName):
dic = {"A":0,"C":1,"G":2,"T":3}
return np.array([ [ dic[e1] for e1 in list(e)] for e in pd.read_csv(fileName,header=None)[0]])
def bagofwords3DataFromCSV(fileName):
X_raw = pd.read_csv(fileName,header=None)
# dictionnaire : string -> integer ex: "AAAA" -> 0, "AAAC" -> 1
dicts = {}
chars = {"A","C","G","T"}
count = 0
for i_0 in chars:
for i_1 in chars:
for i_2 in chars:
dicts[i_0+i_1+i_2] = count
count += 1
def transfer(x):
rel = np.zeros((np.power(4,3)))
for i in range(0,98):
rel[dicts[x[i]+x[i+1]+x[i+2]]] += 1
return rel
return np.array(list(map(lambda x: transfer(x),X_raw[0])))
def bagofwords4DataFromCSV(fileName):
X_raw = pd.read_csv(fileName,header=None)
# dictionnaire : string -> integer ex: "AAAA" -> 0, "AAAC" -> 1
dicts = {}
chars = {"A","C","G","T"}
count = 0
for i_0 in chars:
for i_1 in chars:
for i_2 in chars:
for i_3 in chars:
dicts[i_0+i_1+i_2+i_3] = count
count += 1
def transfer(x):
rel = np.zeros((np.power(4,4)))
for i in range(0,98):
rel[dicts[x[i]+x[i+1]+x[i+2]+x[i+3]]] += 1
return rel
return np.array(list(map(lambda x: transfer(x),X_raw[0])))
def bagofwords5DataFromCSV(fileName):
X_raw = pd.read_csv(fileName,header=None)
# dictionnaire : string -> integer ex: "AAAA" -> 0, "AAAC" -> 1
dicts = {}
chars = {"A","C","G","T"}
count = 0
for i_0 in chars:
for i_1 in chars:
for i_2 in chars:
for i_3 in chars:
for i_4 in chars:
dicts[i_0+i_1+i_2+i_3+i_4] = count
count += 1
def transfer(x):
rel = np.zeros((np.power(4,6)))
for i in range(0,96):
rel[dicts[x[i]+x[i+1]+x[i+2]+x[i+3]+x[i+4]]] += 1
return rel
return np.array(list(map(lambda x: transfer(x),X_raw[0])))
def bagofwords6DataFromCSV(fileName):
X_raw = pd.read_csv(fileName,header=None)
# dictionnaire : string -> integer ex: "AAAA" -> 0, "AAAC" -> 1
dicts = {}
chars = {"A","C","G","T"}
count = 0
for i_0 in chars:
for i_1 in chars:
for i_2 in chars:
for i_3 in chars:
for i_4 in chars:
for i_5 in chars:
dicts[i_0+i_1+i_2+i_3+i_4+i_5] = count
count += 1
def transfer(x):
rel = np.zeros((np.power(4,6)))
for i in range(0,96):
rel[dicts[x[i]+x[i+1]+x[i+2]+x[i+3]+x[i+4]+x[i+5]]] += 1
return rel
return np.array(list(map(lambda x: transfer(x),X_raw[0])))
def bagofwords7DataFromCSV(fileName):
X_raw = pd.read_csv(fileName,header=None)
# dictionnaire : string -> integer ex: "AAAA" -> 0, "AAAC" -> 1
dicts = {}
chars = {"A","C","G","T"}
count = 0
for i_0 in chars:
for i_1 in chars:
for i_2 in chars:
for i_3 in chars:
for i_4 in chars:
for i_5 in chars:
for i_6 in chars:
dicts[i_0+i_1+i_2+i_3+i_4+i_5+i_6] = count
count += 1
def transfer(x):
rel = np.zeros((np.power(4,7)))
for i in range(0,95):
rel[dicts[x[i]+x[i+1]+x[i+2]+x[i+3]+x[i+4]+x[i+5]+x[i+6]]] += 1
return rel
return np.array(list(map(lambda x: transfer(x),X_raw[0])))
def bagofwords8DataFromCSV(fileName):
X_raw = pd.read_csv(fileName,header=None)
# dictionnaire : string -> integer ex: "AAAA" -> 0, "AAAC" -> 1
dicts = {}
chars = {"A","C","G","T"}
count = 0
for i_0 in chars:
for i_1 in chars:
for i_2 in chars:
for i_3 in chars:
for i_4 in chars:
for i_5 in chars:
for i_6 in chars:
for i_7 in chars:
dicts[i_0+i_1+i_2+i_3+i_4+i_5+i_6+i_7] = count
count += 1
def transfer(x):
rel = np.zeros((np.power(4,8)))
for i in range(0,94):
rel[dicts[x[i]+x[i+1]+x[i+2]+x[i+3]+x[i+4]+x[i+5]+x[i+6]+x[i+7]]] += 1
return rel
return np.array(list(map(lambda x: transfer(x),X_raw[0])))
def exportLabelDataFromCSV(fileName):
y_raw = pd.read_csv(fileName)
return np.array(y_raw["Bound"])
def compare_classification_kmeans(X,y):
print("===========Kmeans Comparison===========")
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.33)
clr = Kernel_KMeans()
clr.fit(X_train,y_train)
print("Kernel_KMeans: %f"%(clr.score(X_test,y_test)))
clr = KMeans()
clr.fit(X_train,y_train)
print("My Nearest Centroid: %f"%(clr.score(X_test,y_test)))
clr = NearestCentroid()
clr.fit(X_train,y_train)
print("Sklearn Nearest Centroid: %f"%(clr.score(X_test,y_test)))
def compare_classification_logistic_regression(X,y):
print("===========LG Comparison===========")
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.33)
clr = logistic_regression()
clr.fit(X_train,y_train)
print("My LogisticRegression: %f"%(clr.score(X_test,y_test)))
clr = LogisticRegression()
clr.fit(X_train,y_train)
print("Sklearn LogisticRegression: %f"%(clr.score(X_test,y_test)))
def compare_classification_MultinomialNB(X,y):
print("===========MutinomialNB Comparison===========")
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.33)
clr = MultinomialNB()
clr.fit(X_train,y_train)
print("My Multinomial: %f"%(clr.score(X_test,y_test)))
clr = MyMultinomialNB()
clr.fit(X_train,y_train)
print("Sklearn Multinomial: %f"%(clr.score(X_test,y_test)))
print("")
def proceed_classification(X,y,text="Classification Experiment"):
print("==========="+text+"===========")
X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=0.33)
clr = LogisticRegression()
clr.fit(X_train,y_train)
print("Logistic Regession: %f"%(clr.score(X_test,y_test)))
clr = RidgeClassifier()
clr.fit(X_train,y_train)
print("Ridge: %f"%(clr.score(X_test,y_test)))
clr = MultinomialNB()
clr.fit(X_train,y_train)
print("Multinomial: %f"%(clr.score(X_test,y_test)))
clr = GaussianNB()
clr.fit(X_train,y_train)
print("GaussianNB: %f"%(clr.score(X_test,y_test)))
clr = SGDClassifier()
clr.fit(X_train,y_train)
print("SGDClassifier: %f"%(clr.score(X_test,y_test)))
clr = Perceptron()
clr.fit(X_train,y_train)
print("Perceptron: %f"%(clr.score(X_test,y_test)))
clr = BernoulliNB()
clr.fit(X_train,y_train)
print("BernoulliNB: %f"%(clr.score(X_test,y_test)))
clr = KNeighborsClassifier()
clr.fit(X_train,y_train)
print("KNeighbors: %f"%(clr.score(X_test,y_test)))
clr = NearestCentroid()
clr.fit(X_train,y_train)
print("NearestCentroid: %f"%(clr.score(X_test,y_test)))
clr = RandomForestClassifier()
clr.fit(X_train,y_train)
print("RandomForestClassifier: %f"%(clr.score(X_test,y_test)))
clr = MLPClassifier()
clr.fit(X_train,y_train)
print("Neutral network: %f"%(clr.score(X_test,y_test)))
clr = SVC(kernel="rbf")
clr.fit(X_train,y_train)
print("Kernel SVM network: %f"%(clr.score(X_test,y_test)))
print("\n")
# produire la sortie pour kaggle
def exportResult(classification):
clr = classification()
clr.fit(X_0,y_0)
predict_0 = clr.predict(X_test_0)
clr = classification()
clr.fit(X_1,y_1)
predict_1 = clr.predict(X_test_1)
clr = classification()
clr.fit(X_2,y_2)
predict_2 = clr.predict(X_test_2)
with open('submission.csv', 'w', newline='') as csvfile:
fieldnames = ['Id', 'Bound']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for i, y_i in enumerate(predict_0):
writer.writerow({'Id': i, 'Bound': (int)((y_i+1)/2)})
for i, y_i in enumerate(predict_1):
writer.writerow({'Id': 1000+i, 'Bound': (int)((y_i+1)/2)})
for i, y_i in enumerate(predict_2):
writer.writerow({'Id': 2000+i, 'Bound': (int)((y_i+1)/2)})
print("FINISH: the predicted labels have been wrote into submisson.csv")
def exportFinalResult():
clr = KMeans()
clr.fit(X_0,y_0)
print("Dataset 0: %f"%(clr.score(X_0,y_0)))
predict_0 = clr.predict(X_test_0)
clr = MyMultinomialNB()
clr.fit(X_1,y_1)
print("Dataset 1: %f"%(clr.score(X_1,y_1)))
predict_1 = clr.predict(X_test_1)
clr = MyMultinomialNB()
clr.fit(X_2,y_2)
print("Dataset 2: %f"%(clr.score(X_2,y_2)))
predict_2 = clr.predict(X_test_2)
print(predict_0.shape)
with open('submission12.csv', 'w', newline='') as csvfile:
fieldnames = ['Id', 'Bound']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for i, y_i in enumerate(predict_0):
writer.writerow({'Id': i, 'Bound': (int)((y_i+1)/2)})
for i, y_i in enumerate(predict_1):
writer.writerow({'Id': 1000+i, 'Bound': (int)((y_i+1)/2)})
for i, y_i in enumerate(predict_2):
writer.writerow({'Id': 2000+i, 'Bound': (int)((y_i+1)/2)})
# change the size of word bag
bagofwordsDataFromCSV = bagofwords6DataFromCSV
X_raw_0 = ger_raw_data("Xtr0.csv")
X_raw_1 = ger_raw_data("Xtr1.csv")
X_raw_2 = ger_raw_data("Xtr2.csv")
X_0 = bagofwordsDataFromCSV("Xtr0.csv")
X_1 = bagofwordsDataFromCSV("Xtr1.csv")
X_2 = bagofwordsDataFromCSV("Xtr2.csv")
y_0 = exportLabelDataFromCSV("Ytr0.csv")
y_1 = exportLabelDataFromCSV("Ytr1.csv")
y_2 = exportLabelDataFromCSV("Ytr2.csv")
X_test_0 = bagofwordsDataFromCSV("Xte0.csv")
X_test_1 = bagofwordsDataFromCSV("Xte1.csv")
X_test_2 = bagofwordsDataFromCSV("Xte2.csv")
def classification_experiment():
print("===============================================")
print("===========Classification Experiment===========")
print("===============================================")
print("\n")
print("Raw Data - Dataset 0")
proceed_classification(X_raw_0,y_0)
print("Raw Data - Dataset 1")
proceed_classification(X_raw_1,y_1)
print("Raw Data - Dataset 2")
proceed_classification(X_raw_2,y_2)
print("6-gram Data - Dataset 0")
proceed_classification(X_0,y_0)
print("6-gram Data - Dataset 1")
proceed_classification(X_1,y_1)
print("6-gram Data - Dataset 2")
proceed_classification(X_2,y_2)
def exportResult3(classification):
clr = Kernel_KMeans()
clr.fit(X_0,y_0)
print("Dataset 0: %f"%(clr.score(X_0,y_0)))
predict_0 = clr.predict(X_test_0)
clr = classification()
clr.fit(X_1,y_1)
print("Dataset 1: %f"%(clr.score(X_1,y_1)))
predict_1 = clr.predict(X_test_1)
clr = Kernel_KMeans()
clr.fit(X_2,y_2)
print("Dataset 2: %f"%(clr.score(X_2,y_2)))
predict_2 = clr.predict(X_test_2)
print(predict_0.shape)
with open('submission9.csv', 'w', newline='') as csvfile:
fieldnames = ['Id', 'Bound']
writer = csv.DictWriter(csvfile, fieldnames=fieldnames)
writer.writeheader()
for i, y_i in enumerate(predict_0):
writer.writerow({'Id': i, 'Bound': (int)((y_i+1)/2)})
for i, y_i in enumerate(predict_1):
writer.writerow({'Id': 1000+i, 'Bound': (int)((y_i+1)/2)})
for i, y_i in enumerate(predict_2):
writer.writerow({'Id': 2000+i, 'Bound': (int)((y_i+1)/2)})
if __name__ == '__main__':
classification_experiment()
compare_classification_logistic_regression(X_0,y_0)
compare_classification_kmeans(X_0,y_0)
compare_classification_MultinomialNB(X_0,y_0)